
# Import Packages

import pandas as pd
import numpy as np

# Plotting
import matplotlib.pyplot as plt
import plotly.express as px
import squarify                            # algorithm for treemap
import seaborn as sns                      # data visualization library based on matplotlib
import plotly.graph_objects as go          # interactive data analysis with Plotly
from plotly.subplots import make_subplots  # construct figures with arbitrary subplots
from PIL import Image                      # represent a PIL image
from wordcloud import WordCloud, STOPWORDS, ImageColorGenerator  # create WordCloud


import warnings
warnings.filterwarnings('ignore')


# Concatenate all Washington DC csv

DC_data_lst = []
for i in range(20, 320, 20):
    data = pd.read_csv("Airbnb Washington DC {}-{} places.csv".format(i-20, i), sep = ",")
    DC_data_lst.append(data)
DC_data = pd.concat(DC_data_lst)


# drop unuseful column and add a area column

DC_data.drop(['Unnamed: 0'], axis = 1, inplace = True)
DC_data['Area'] = 'Washington DC'


DC_data.head()


# Concatenate all Virginia csv

VA_data_lst = []
for i in range(20, 320, 20):
    data = pd.read_csv("Airbnb Virginia {}-{} places.csv".format(i-20, i), sep = ",")
    VA_data_lst.append(data)
VA_data = pd.concat(VA_data_lst)


# drop unuseful column and add a area column

VA_data.drop(['Unnamed: 0'], axis = 1, inplace = True)
VA_data['Area'] = 'Virginia'


VA_data.head()


# Concatenate all Maryland csv

MA_data_lst = []
for i in range(20, 320, 20):
    data = pd.read_csv("Airbnb Maryland {}-{} places.csv".format(i-20, i), sep = ",")
    MA_data_lst.append(data)
MA_data = pd.concat(MA_data_lst)


# drop unuseful column and add a area column

MA_data.drop(['Unnamed: 0'], axis = 1, inplace = True)
MA_data['Area'] = 'Maryland'


MA_data.head()


# Concatenate DMV data and delete duplicate rows

data = pd.concat([DC_data, VA_data, MA_data])
data.drop_duplicates(subset = ['Title'], inplace = True)
data.reset_index(drop = True, inplace = True)
data.index += 1


print(data.shape)
data

(706, 25)


# Create a wordcloud to see what locations that comes up frequently

Location = " ".join(location for location in data['Location']) 

wordcloud = WordCloud(
                      width = 3000, 
                      height = 1500,
                      background_color = 'white',
                      max_font_size = 1000
                      ).generate(Location)

plt.figure(figsize = [30, 10])
plt.imshow(wordcloud, interpolation = 'bilinear')
plt.axis("off")
plt.show()


# Create a wordcloud to see what words in title that hosts created that comes up frequently

Title = " ".join(title for title in data['Title'])
mask = np.array(Image.open("House.jpg"))
wordcloud = WordCloud(
                      width = 4000, 
                      height = 2000,
                      background_color = 'black',
                      mask = mask
                      ).generate(Title)

image_colors = ImageColorGenerator(mask)
plt.figure(figsize = [30,15])
plt.imshow(wordcloud.recolor(color_func = image_colors), interpolation = 'bilinear')
plt.axis("off")
plt.show()


# Count the number of each unique property type in DMV area
data_by_type_counts = data.groupby(by = ['Type']).size().reset_index(name = 'Counts')

# Calculaue the median price of each unique property type in DMV area (Since price range is large, median price makes more sense)
data_by_type_price = data.groupby(by = ['Type'])['Price (per Night)'].median().reset_index(name = 'Median Price (per Night)')

# Merge two datasets into one and sort count number in descending order
data_by_type_counts_price = pd.merge(data_by_type_counts, data_by_type_price, on=['Type'])
data_by_type_counts_price = data_by_type_counts_price.sort_values(['Counts'], ascending = False)
data_by_type_counts_price


# Create a pie chart to display the percentage of each unique property type of lodging and their median prices
# per night in DMV area

pull = [0] * 30
pull[0] = 0.1

pie_DMV = go.Pie(
                 labels = data_by_type_counts_price['Type'],
                 values = data_by_type_counts_price['Counts'],
                 text = data_by_type_counts_price['Median Price (per Night)'],
                 pull = pull,
                 name = 'DMV area'
                )

d = [pie_DMV]

layout = go.Layout(
                   height = 600,
                   width = 1000,
                   title = go.layout.Title(text = 'The Percentage of each Property Type of Lodging in DMV Area ' + '({} types)'.format(data_by_type_counts_price.shape[0]) + '<br>Hover For Median Price (per Night)'),
                   legend = dict(title = "Type:",
                                 yanchor = "top",
                                 y = 1.0,
                                 xanchor="left",
                                 x = -0.7)
                   )
fig = go.Figure(data = d, layout = layout)

fig.update_traces( 
                  hovertemplate = '<b>%{label}:</b><br>Counts: %{value} </br>Median Price (per Night): %{text: $.1f}',
                  texttemplate = '<b>%{label}:</b> %{percent} (%{value})',   
                  textposition = 'auto'
                  )

fig.show()


# Count the number of property type of lodging in different area
data_by_area_type_counts = data.groupby(by = ['Area', 'Type']).size().reset_index(name = 'Counts')

# Calculate the median price of different property type of lodging in different area
data_by_area_type_price = data.groupby(by = ['Area', 'Type'])['Price (per Night)'].median().reset_index(name = 'Median Price (per Night)')

# Merge two datasets into one and sort count number in ascending order
data_by_area_type_counts_price = pd.merge(data_by_area_type_counts, data_by_area_type_price, on=['Area', 'Type'])
data_by_area_type_counts_price = data_by_area_type_counts_price.sort_values(['Area', 'Counts'], ascending = True)
data_by_area_type_counts_price


# Create four bar charts with dropdown menus to display the counts of different property types of lodging and 
# their median prices per night in a different area.

bar_DC = go.Bar(
                x = data_by_area_type_counts_price[data_by_area_type_counts_price['Area'] == 'Washington DC']['Counts'],
                y = data_by_area_type_counts_price[data_by_area_type_counts_price['Area'] == 'Washington DC']['Type'],
                text = data_by_area_type_counts_price[data_by_area_type_counts_price['Area'] == 'Washington DC']['Median Price (per Night)'],
                orientation = 'h',
                marker_color = 'gold',
                name = 'Washington DC'
                )

bar_VA = go.Bar(
                x = data_by_area_type_counts_price[data_by_area_type_counts_price['Area'] == 'Virginia']['Counts'],
                y = data_by_area_type_counts_price[data_by_area_type_counts_price['Area'] == 'Virginia']['Type'],
                text = data_by_area_type_counts_price[data_by_area_type_counts_price['Area'] == 'Virginia']['Median Price (per Night)'],
                orientation = 'h',
                marker_color = 'deepskyblue',
                name = 'Virginia'
                )

bar_MD = go.Bar(
                x = data_by_area_type_counts_price[data_by_area_type_counts_price['Area'] == 'Maryland']['Counts'],
                y = data_by_area_type_counts_price[data_by_area_type_counts_price['Area'] == 'Maryland']['Type'],
                text = data_by_area_type_counts_price[data_by_area_type_counts_price['Area'] == 'Maryland']['Median Price (per Night)'],
                orientation = 'h',
                marker_color = 'pink',
                name = 'Maryland'
                )

d = [bar_DC, bar_VA, bar_MD]

layout = go.Layout(
                   height = 800, 
                   width = 1000,  
                   xaxis = dict(title = "Counts"),
                   yaxis = dict(title = "Property Type")
                  )

fig = go.Figure(data = d, layout = layout)

    
fig.update_layout(
                  barmode = 'stack',
                  updatemenus = [go.layout.Updatemenu(
                  active = 0, 
                  buttons = list([
                  dict(label =  'Comparison of DMV area',
                       method = 'update',
                       args = [{'showlegend':True}]), 
                      
                  dict(label = 'Washington DC',
                       method = 'update',
                       args = [{'visible': [True, False, False]}, 
                               {'title': 'Counts of Different Property Type of Lodging and Compare their Median Price in Washington DC ' + '({} types)'.format(data_by_area_type_counts_price[data_by_area_type_counts_price['Area'] == 'Washington DC'].shape[0]),
                                'showlegend':True}]),
                      
                  dict(label = 'Virginia',
                       method = 'update',
                       args = [{'visible': [False, True, False]},
                               {'title': 'Counts of Different Property Type of Lodging and Compare their Median Price in Virginia ' + '({} types)'.format(data_by_area_type_counts_price[data_by_area_type_counts_price['Area'] == 'Virginia'].shape[0]),
                                'showlegend':True}]),
                      
                  dict(label = 'Maryland',
                       method = 'update',
                       args = [{'visible': [False, False, True]},
                               {'title': 'Counts of Different Property Type of Lodging and Compare their Median Price in Maryland ' + '({} types)'.format(data_by_area_type_counts_price[data_by_area_type_counts_price['Area'] == 'Maryland'].shape[0]),
                                'showlegend':True}]),
                                 ]),
                      
                  direction = 'down',
                  pad = {'r': 10, 't': 10},
                  showactive = True,
                  x = -0.15,
                  xanchor = 'right',
                  y = 0.98,
                  yanchor = 'bottom'
                                                     ),
                  ])
fig.update_traces(
                  hovertemplate = "<b>%{y}:</b><br>Counts: %{x} </br>Median Price (per Night): %{text: $.1f}",
                  texttemplate = '%{text:$.1f}', 
                  textposition = 'auto'
                  )

fig.show()


# convert boolean variables into dummy/indicator variables

data_amenities_dummies = pd.get_dummies(data, columns = ['Air Conditioning', 'Wifi', 'Washer', 'Kitchen', 'Breakfast', 'Pets allowed', 'Free parking', 'Elevator', 'Gym', 'Indoor fireplace', 'Pool'], drop_first = True)
data_amenities_dummies


# Create a correlation matrix to display the correlation coefficients between variables

corr = data_amenities_dummies.corr()
corr.style.background_gradient(cmap = 'YlOrBr', text_color_threshold = 0.5).set_precision(2)


# Create a plot that contains three boxplot subplots to display different room structure and different number 
# of guests that can be accommodatedin a different area

fig, axes = plt.subplots(1, 3, figsize = (32, 8))

fig.suptitle('Compare the Room Structure and Number of Guests in Different Area', fontsize = 30)

sns.set(rc = {'axes.grid' : True,
              'axes.labelsize' : 25,
              'xtick.labelsize' : 18,
              'ytick.labelsize' : 20})

sns.boxplot(ax = axes[0], 
            data = data[data['Area'] == 'Washington DC'][['Number of Guest', 'Number of Bedroom', 'Number of Bed', 'Number of Bath']], 
            width = 0.5, 
           ).set(xlabel = 'Washington DC', ylabel = 'Number')

sns.boxplot(ax = axes[1], 
            data=data[data['Area'] == 'Virginia'][['Number of Guest', 'Number of Bedroom', 'Number of Bed', 'Number of Bath']],
            width = 0.5
           ).set(xlabel = 'Virginia', ylabel = 'Number')

sns.boxplot(ax = axes[2], 
            data=data[data['Area'] == 'Maryland'][['Number of Guest', 'Number of Bedroom', 'Number of Bed', 'Number of Bath']],
            width = 0.5
           ).set(xlabel = 'Maryland', ylabel = 'Number')

fig.autofmt_xdate(rotation = 25)
plt.show()


# To make the data more representative, drop rows that include NaN

data_structure = data[['Area', 'Number of Guest', 'Number of Bedroom', 'Number of Bed', 'Number of Bath', 'Price (per Night)']].dropna()
data_structure


# Create a 3d Scatter Plot to display each lodgings' room structure, number of guests, and price in the DMV area

fig = px.scatter_3d(
                    data_structure, 
                    x = 'Number of Guest', 
                    y = 'Number of Bedroom', 
                    z ='Number of Bed', 
                    size = 'Number of Bath',
                    size_max = 66,
                    color = 'Price (per Night)',
                    hover_name = 'Area'
                    )

fig.update_layout(
                  scene_zaxis_type = "log",
                  height = 600,
                  width = 1000,
                  title = go.layout.Title(text = "Different Room Structure of Lodging with their Price in DMV area")
                 )

fig.update_traces(hovertemplate = "<b>%{hovertext}:</b> <br>Number of Guest: %{x} </br>Number of Bedroom: %{y} </br>Number of Bed: %{z} </br>Number of Bath: %{marker.size} </br>Price (per Night): %{marker.color:$.1f}",)

fig.show()


# Count the number of amenities and facilities have in lodgings in DMV area

data_dmv_amenities_counts = data_amenities_dummies.iloc[:,-11:].sum().reset_index()
data_dmv_amenities_counts.rename(columns = {'index' : 'Type', 0 : 'Counts'}, inplace = True)
data_dmv_amenities_counts = data_dmv_amenities_counts.replace('_Yes','', regex = True)
data_dmv_amenities_counts


# Create a squarify tree plot to display proportion of each amenities and facilities

plt.figure(figsize = (20, 10))
squarify.plot(sizes = data_dmv_amenities_counts['Counts'], 
              label = data_dmv_amenities_counts['Type'],
              text_kwargs = {'fontsize': 18},
              alpha = 0.55)

plt.axis('off')
plt.title('Amenities and Facilities', fontsize = 23, fontweight = "bold")
plt.show()


data_area_amenities_dummies = data_amenities_dummies.iloc[:,-12:]

# Count the number of lodgings in different area
data_by_area_size = data.groupby(by = ['Area']).size().reset_index(name = 'Number of Lodgings')

# Sum the number of yes of each amenities and facilities
data_amenities_yes = data_area_amenities_dummies.groupby(['Area']).sum().reset_index()

# Calculate the percentage of each amenities and facilities in each area
data_amenities_percentage = data_amenities_yes.iloc[:,1:].div(data_by_area_size['Number of Lodgings'], axis = 0) * 100

# Remove the suffix of columns' name and add area column
data_amenities_percentage.columns = data_amenities_percentage.columns.str.replace(r'_Yes$', '')
data_amenities_percentage['Area'] = ['Maryland', 'Virginia', 'Washington DC']

# Transpose dataframe
data_amentities_percentage_transpose = data_amenities_percentage.set_index(['Area']).transpose().reset_index()
data_amentities_percentage_transpose.rename(columns = {'index' : 'Amentities and Facilities'}, inplace = True)
data_amentities_percentage_transpose


# Create four bar charts with dropdown menus to display the proportion of each amenities and facilities 
# in different area.

bar_MD = go.Bar(
                x = data_amentities_percentage_transpose['Amentities and Facilities'],
                y = data_amentities_percentage_transpose['Maryland'], 
                marker_color = 'pink',
                name = 'Maryland'
                )

bar_VA = go.Bar(
                x = data_amentities_percentage_transpose['Amentities and Facilities'],
                y = data_amentities_percentage_transpose['Virginia'], 
                marker_color = 'deepskyblue',
                name = 'Virginia'
                )

bar_DC = go.Bar(
                x = data_amentities_percentage_transpose['Amentities and Facilities'],
                y = data_amentities_percentage_transpose['Washington DC'], 
                marker_color = 'gold',
                name = 'Washington DC'
                )

d = [bar_MD, bar_VA, bar_DC]

layout = go.Layout(
                   height = 600, 
                   width =1000,  
                   xaxis = dict(title = "Amentities and Facilities"),
                   yaxis = dict(title = "Percentage %")
                  )

fig = go.Figure(data = d, layout = layout)

fig.update_layout(
                  updatemenus = [go.layout.Updatemenu(
                  active = 0, 
                  buttons = list([
                  dict(label =  'Comparison of DMV Area',
                       method = 'update',
                       args = [{'showlegend':True}]), 
                      
                  dict(label = 'Maryland',
                       method = 'update',
                       args = [{'visible': [True, False, False]}, 
                               {'title': 'Percentage of Amentities and Facilities in Maryland',
                                'showlegend':True}]),
                      
                  dict(label = 'Virginia',
                       method = 'update',
                       args = [{'visible': [False, True, False]},
                               {'title': 'Percentage of Amentities and Facilities in Virginia',
                                'showlegend':True}]),
                      
                  dict(label = 'Washington DC',
                       method = 'update',
                       args = [{'visible': [False, False, True]},
                               {'title': 'Percentage of Amentities and Facilities in Washington DC',
                                'showlegend':True}]),
                                 ]),
                      
                  direction = 'down',
                  pad = {'r': 10, 't': 10},
                  showactive = True,
                  x = -0.05,
                  xanchor = 'right',
                  y = 1.0,
                  yanchor = 'bottom'
                                                     ),
                  ])

fig.update_traces(hovertemplate = "<b>%{x}:</b> <br>Percentage: %{y:.2f}%")

fig.show()


# Sort variables

data_popular = data.sort_values(['Reviews', 'Rate (out of 5)', 'Price (per Night)'], ascending = (False, False, True))
data_popular.head(10)


# Create four subplots to each area to display the top ten popular with best price lodgings' property type, 
# room structure, facilities and facilities they offer, and the summary of price and rate, separately.

# Create 12 subplots
fig = make_subplots(rows = 3, cols = 4, 
                    specs = [[{'type' : 'xy'}, {'type' : 'xy'}, {'type' : 'polar'}, {'type' : 'table'}],
                             [{'type' : 'xy'}, {'type' : 'xy'}, {'type' : 'polar'}, {'type' : 'table'}],
                             [{'type' : 'xy'}, {'type' : 'xy'}, {'type' : 'polar'}, {'type' : 'table'}]],
                    subplot_titles = ('', '', '', 'Washington DC', '', '', '', 'Virginia', '', '', '', 'Maryland'))


# Top 10 popular lodgings with best price in Washington DC

data_popular_DC = data_popular[data_popular['Area'] == 'Washington DC'][:10]

# The property type of top 10 popular lodgings with best price
data_popular_DC_type = data_popular_DC.groupby(by = ['Type']).size().reset_index(name = 'Counts')
data_popular_DC_type.sort_values(['Counts'], ascending = False, inplace = True)

# The amentities and facilities of top 10 popular lodgings with best price have
data_popular_DC_amenities = data_popular_DC[['Air Conditioning', 'Wifi', 'Washer', 'Kitchen', 'Breakfast', 'Pets allowed', 'Free parking', 'Elevator', 'Gym', 'Indoor fireplace', 'Pool']].transpose().reset_index()
data_popular_DC_amenities['Counts'] = (data_popular_DC_amenities.iloc[:, :] == 'Yes').sum(axis = 1)

# The statistical summary of price and rate of top 10 popular lodgings with best price
data_popular_DC_describe = data_popular_DC[['Rate (out of 5)', 'Reviews', 'Price (per Night)']].describe().reset_index()
data_popular_DC_describe = data_popular_DC_describe.iloc[[1,3,5,7],:]
data_popular_DC_describe.rename(columns = {'index':'Stateistics'}, inplace = True)
data_popular_DC_describe = data_popular_DC_describe.round(2)

trace1 = go.Bar(
                x = data_popular_DC_type['Type'],
                y = data_popular_DC_type['Counts'],
                marker_color = 'gold',
                hovertemplate = "<b>%{x}:</b> <br>Counts: %{y}",
                name = 'Washington DC'
                )

trace2 = go.Box(
                y = data_popular_DC['Number of Guest'],
                name = 'Number of Guest'
                )

trace3 = go.Box(
                y = data_popular_DC['Number of Bedroom'],
                name = 'Number of Bedroom'
                )

trace4 = go.Box(
                y = data_popular_DC['Number of Bed'],
                name = 'Number of Bed'
                )

trace5 = go.Box(
                y = data_popular_DC['Number of Bath'],
                name = 'Number of Bath'
                )

trace6 = go.Scatterpolar(
                         r = data_popular_DC_amenities['Counts'],
                         theta = data_popular_DC_amenities['index'],
                         fill = 'toself',
                         fillcolor = 'gold',
                         hovertemplate = "<b>%{theta}:</b> <br>Counts: %{r}",
                         opacity = 0.9,
                         hoverlabel = dict(bgcolor = 'gold'),
                         line = dict(color = 'gold'),
                         name = 'Washington DC'
                         )

trace7 = go.Table(
                  header = dict(values = list(data_popular_DC_describe.columns),
                                fill_color = 'gold',
                                font = dict(size = 12),
                                align = 'center'),
                  cells = dict(values = [data_popular_DC_describe['Stateistics'], data_popular_DC_describe['Rate (out of 5)'], data_popular_DC_describe['Reviews'], data_popular_DC_describe['Price (per Night)']],
                               align = 'center'))
                  
# display each trace in particual subplot
fig.append_trace(trace1, 1, 1)
fig.append_trace(trace2, 1, 2)
fig.append_trace(trace3, 1, 2)
fig.append_trace(trace4, 1, 2)
fig.append_trace(trace5, 1, 2)
fig.append_trace(trace6, 1, 3)
fig.append_trace(trace7, 1, 4)


# Top 10 popular lodgings with best price in Virginia

data_popular_VA = data_popular[data_popular['Area'] == 'Virginia'][:10]

data_popular_VA_type = data_popular_VA.groupby(by = ['Type']).size().reset_index(name = 'Counts')
data_popular_VA_type.sort_values(['Counts'], ascending = False, inplace = True)

data_popular_VA_amenities = data_popular_VA[['Air Conditioning', 'Wifi', 'Washer', 'Kitchen', 'Breakfast', 'Pets allowed', 'Free parking', 'Elevator', 'Gym', 'Indoor fireplace', 'Pool']].transpose().reset_index()
data_popular_VA_amenities['Counts'] = (data_popular_VA_amenities.iloc[:, :] == 'Yes').sum(axis = 1)

data_popular_VA_describe = data_popular_VA[['Rate (out of 5)', 'Reviews', 'Price (per Night)']].describe().reset_index()
data_popular_VA_describe = data_popular_VA_describe.iloc[[1,3,5,7],:]
data_popular_VA_describe.rename(columns = {'index':'Stateistics'}, inplace = True)
data_popular_VA_describe = data_popular_VA_describe.round(2)

trace11 = go.Bar(
                x = data_popular_VA_type['Type'],
                y = data_popular_VA_type['Counts'],
                marker_color = 'deepskyblue',
                hovertemplate = "<b>%{x}:</b> <br>Counts: %{y}",
                name = 'Virginia'
                )

trace22 = go.Box(
                y = data_popular_VA['Number of Guest'],
                name = 'Number of Guest'
                )

trace33 = go.Box(
                y = data_popular_VA['Number of Bedroom'],
                name = 'Number of Bedroom'
                )

trace44 = go.Box(
                y = data_popular_VA['Number of Bed'],
                name = 'Number of Bed'
                )

trace55 = go.Box(
                y = data_popular_VA['Number of Bath'],
                name = 'Number of Bath'
                )

trace66 = go.Scatterpolar(
                         r = data_popular_VA_amenities['Counts'],
                         theta = data_popular_VA_amenities['index'],
                         fill = 'toself',
                         fillcolor = 'deepskyblue',
                         hovertemplate = "<b>%{theta}:</b> <br>Counts: %{r}",
                         opacity = 0.9,
                         hoverlabel = dict(bgcolor = 'deepskyblue'),
                         line = dict(color = 'deepskyblue'),
                         name = 'Virginia'
                         )

trace77 = go.Table(
                  header = dict(values = list(data_popular_VA_describe.columns),
                                fill_color = 'deepskyblue',
                                font = dict(size = 12),
                                align = 'center'),
                  cells = dict(values = [data_popular_VA_describe['Stateistics'], data_popular_VA_describe['Rate (out of 5)'], data_popular_VA_describe['Reviews'], data_popular_VA_describe['Price (per Night)']],
                               align = 'center'))
                  
fig.append_trace(trace11, 2, 1)
fig.append_trace(trace22, 2, 2)
fig.append_trace(trace33, 2, 2)
fig.append_trace(trace44, 2, 2)
fig.append_trace(trace55, 2, 2)
fig.append_trace(trace66, 2, 3)
fig.append_trace(trace77, 2, 4)


# Top 10 popular lodgings with best price in Maryland

data_popular_MD = data_popular[data_popular['Area'] == 'Maryland'][:10]

data_popular_MD_type = data_popular_MD.groupby(by = ['Type']).size().reset_index(name = 'Counts')
data_popular_MD_type.sort_values(['Counts'], ascending = False, inplace = True)

data_popular_MD_amenities = data_popular_MD[['Air Conditioning', 'Wifi', 'Washer', 'Kitchen', 'Breakfast', 'Pets allowed', 'Free parking', 'Elevator', 'Gym', 'Indoor fireplace', 'Pool']].transpose().reset_index()
data_popular_MD_amenities['Counts'] = (data_popular_MD_amenities.iloc[:, :] == 'Yes').sum(axis = 1)

data_popular_MD_describe = data_popular_MD[['Rate (out of 5)', 'Reviews', 'Price (per Night)']].describe().reset_index()
data_popular_MD_describe = data_popular_MD_describe.iloc[[1,3,5,7],:]
data_popular_MD_describe.rename(columns = {'index':'Stateistics'}, inplace = True)
data_popular_MD_describe = data_popular_MD_describe.round(2)

trace111 = go.Bar(
                x = data_popular_MD_type['Type'],
                y = data_popular_MD_type['Counts'],
                marker_color = 'pink',
                hovertemplate = "<b>%{x}:</b> <br>Counts: %{y}",
                name = 'Maryland'
                )

trace222 = go.Box(
                y = data_popular_MD['Number of Guest'],
                name = 'Number of Guest'
                )

trace333 = go.Box(
                y = data_popular_MD['Number of Bedroom'],
                name = 'Number of Bedroom'
                )

trace444 = go.Box(
                y = data_popular_MD['Number of Bed'],
                name = 'Number of Bed'
                )

trace555 = go.Box(
                y = data_popular_MD['Number of Bath'],
                name = 'Number of Bath'
                )

trace666 = go.Scatterpolar(
                         r = data_popular_MD_amenities['Counts'],
                         theta = data_popular_MD_amenities['index'],
                         fill = 'toself',
                         fillcolor = 'pink',
                         hovertemplate = "<b>%{theta}:</b> <br>Counts: %{r}",
                         opacity = 0.9,
                         hoverlabel = dict(bgcolor = 'pink'),
                         line = dict(color = 'pink'),
                         name = 'Maryland'
                         )

trace777 = go.Table(
                  header = dict(values = list(data_popular_MD_describe.columns),
                                fill_color = 'pink',
                                font = dict(size = 12),
                                align = 'center'),
                  cells = dict(values = [data_popular_MD_describe['Stateistics'], data_popular_MD_describe['Rate (out of 5)'], data_popular_MD_describe['Reviews'], data_popular_MD_describe['Price (per Night)']],
                               align = 'center'))
                  
fig.append_trace(trace111, 3, 1)
fig.append_trace(trace222, 3, 2)
fig.append_trace(trace333, 3, 2)
fig.append_trace(trace444, 3, 2)
fig.append_trace(trace555, 3, 2)
fig.append_trace(trace666, 3, 3)
fig.append_trace(trace777, 3, 4)

fig.update_yaxes(title_text = 'Washington DC', row = 1, col = 1)
fig.update_yaxes(title_text = 'Virginia', row = 2, col = 1)
fig.update_yaxes(title_text = 'Maryland', row = 3, col = 1)

fig.update_layout(height = 1000,
                  width = 1450,
                  showlegend = False,
                  title_text = 'Compare Top 10 Popular Lodgings with Best Price in Different Area') 

fig.show()


# Add Rate Scale column in dataframe

Rate_scale_lst = []
for i in data['Rate (out of 5)']:
    if i <= 3.5:
        Rate_scale_lst.append('Below 3.5')
    elif 3.5 < i <= 4.0:
        Rate_scale_lst.append('3.5-4.0')
    elif 4.0 < i <= 4.5:
        Rate_scale_lst.append('4.0-4.5')
    elif 4.5 < i <= 5.0:
        Rate_scale_lst.append('4.5-5.0')
    else:
        Rate_scale_lst.append('NaN')

data['Rate Scale'] = np.array(Rate_scale_lst)


# Add Price Scale column in dataframe

Price_scale_lst = []
for i in data['Price (per Night)']:
    if i <= 50:
        Price_scale_lst.append('Below 50')
    elif 50 < i <= 100:
        Price_scale_lst.append('50-100')
    elif 100 < i <= 150:
        Price_scale_lst.append('100-150')
    elif 150 < i <= 200:
        Price_scale_lst.append('150-200')
    elif i > 200:
        Price_scale_lst.append('Over 200')
    else:
        Price_scale_lst.append('NaN')

data['Price Scale'] = np.array(Price_scale_lst)


def main():
    print('Welcome to the Airbnb Filter and Recomendation in DMV area!') 
    
    Area = ''
    while Area != 'q':
        area_menu()
        Area = input('*** What are you going to stay in DMV area? (select number): ')
        response = area_filter(Area)
        if response == 'q':
            print('*** Quit the program successful!')
            break

def area_menu():
    print()
    print('DMV area')
    print()
    print('1. Washington DC')
    print('2. Virginia')
    print('3. Maryland')
    print('q. Quit the program')
    print()

    
def rate_scale_menu():
    print()
    print('Rate Scale')
    print()
    print('1. Below 3.5')
    print('2. 3.5 - 4.0')
    print('3. 4.0 - 4.5')
    print('4. 4.5 - 5.0')
    print('q. Quit the program')
    print()    
    

def price_scale_menu():
    print()
    print('Price Scale')
    print()
    print('1. Below $50')
    print('2. $50 - $100')
    print('3. $100 - $150')
    print('4. $150 - $200')
    print('5. Over $200')
    print('q. Quit the program')
    print()     


def area_filter(Area):
    print()
    if Area == '1':
        DC_data = data[data['Area'] == 'Washington DC']
        print('* {} results *'.format(DC_data.shape[0]))
        guest_filter(DC_data)
    elif Area == '2':
        VA_data = data[data['Area'] == 'Virginia']
        print('* {} results *'.format(VA_data.shape[0]))
        guest_filter(VA_data)
    elif Area == '3':
        MD_data = data[data['Area'] == 'Maryland']
        print('* {} results *'.format(MD_data.shape[0]))
        guest_filter(MD_data)
    else:
        return 'q'

        
def guest_filter(area_data):
    print()
    Guest = int(input('*** Add guest (number): '))
    print()
    area_guest_data = area_data[area_data['Number of Guest'] == Guest]
    if area_guest_data.shape[0] != 0:
        print('* {} results with below information *'.format(area_guest_data.shape[0]))
        area_guest_data_rate_count = area_guest_data.groupby(by = ['Rate Scale']).size().reset_index(name = 'Counts')
        print()
        print('***********************')
        print(area_guest_data_rate_count.set_index(['Rate Scale']))
        print('***********************')
        rate_filter(area_guest_data)
    else:
        print('*** Sorry, no result.')
       

    
def rate_filter(area_guest_data):
    print()
    rate_scale_menu()
    Rate = input('*** What is your expected rating? (select number): ')
    print()
    if Rate == '1':
        area_guest_rate_data = area_guest_data[area_guest_data['Rate Scale'] == 'Below 3.5']
        rate_return_function(area_guest_rate_data)  
    elif Rate == '2':
        area_guest_rate_data = area_guest_data[area_guest_data['Rate Scale'] == '3.5-4.0']
        rate_return_function(area_guest_rate_data)
    elif Rate == '3':
        area_guest_rate_data = area_guest_data[area_guest_data['Rate Scale'] == '4.0-4.5']
        rate_return_function(area_guest_rate_data)
    elif Rate == '4':
        area_guest_rate_data = area_guest_data[area_guest_data['Rate Scale'] == '4.5-5.0']
        rate_return_function(area_guest_rate_data)
    else:
        print('*** Sorry, no result.')

        
def rate_return_function(area_guest_rate_data):
    if area_guest_rate_data.shape[0] != 0:
        print('* {} results with below information *'.format(area_guest_rate_data.shape[0]))
        area_guest_rate_price_count = area_guest_rate_data.groupby(by = ['Price Scale']).size().reset_index(name = 'Counts')
        print()
        print('***********************')
        print(area_guest_rate_price_count.set_index(['Price Scale']))
        print('***********************')
        price_filter(area_guest_rate_data)
    else:
        print('*** Sorry, no result.') 

        
def price_filter(area_guest_rate_data):
    print()
    price_scale_menu()
    Price = input('*** What is your expected price? (select number): ')
    print()
    if Price == '1':
        area_guest_rate_price_data = area_guest_rate_data[area_guest_rate_data['Price Scale'] == 'Below 50']
        price_return_function(area_guest_rate_price_data)       
    elif Price == '2':
        area_guest_rate_price_data = area_guest_rate_data[area_guest_rate_data['Price Scale'] == '50-100']
        price_return_function(area_guest_rate_price_data)         
    elif Price == '3':
        area_guest_rate_price_data = area_guest_rate_data[area_guest_rate_data['Price Scale'] == '100-150']
        price_return_function(area_guest_rate_price_data)       
    elif Price == '4':
        area_guest_rate_price_data = area_guest_rate_data[area_guest_rate_data['Price Scale'] == '150-200']
        price_return_function(area_guest_rate_price_data)         
    elif Price == '5':
        area_guest_rate_price_data = area_guest_rate_data[area_guest_rate_data['Price Scale'] == 'Over 200']
        price_return_function(area_guest_rate_price_data)

        
def price_return_function(area_guest_rate_price_data):
    if area_guest_rate_price_data.shape[0] != 0:
        print()
        print('* {} results *'.format(area_guest_rate_price_data.shape[0]))
        print()
        print('******* Top 5 Recomendation *******')
        if area_guest_rate_price_data.shape[0] < 5:
            area_guest_rate_price_data.sort_values(['Reviews'], ascending = False, inplace = True)
            r = 0
            while r < area_guest_rate_price_data.shape[0]:
                print()
                title = [str(x) for x in area_guest_rate_price_data['Title']][r]
                rate = [str(x) for x in area_guest_rate_price_data['Rate (out of 5)']][r]
                reviews = [str(x) for x in area_guest_rate_price_data['Reviews']][r]
                price = [str(x) for x in area_guest_rate_price_data['Price (per Night)']][r]
                link = [str(x) for x in area_guest_rate_price_data['Link']][r]
                print('{}. {}'.format(r+1, title))
                print('******** {}({}) ********* ${}/night *********'.format(rate, reviews, price))
                print(link)
                print()
                r += 1
        else:         
            area_guest_rate_price_data.sort_values(['Reviews'], ascending = False, inplace = True)
            r = 0
            while r < 5:
                print()
                title = [str(x) for x in area_guest_rate_price_data['Title']][r]
                rate = [str(x) for x in area_guest_rate_price_data['Rate (out of 5)']][r]
                reviews = [str(x) for x in area_guest_rate_price_data['Reviews']][r]
                price = [str(x) for x in area_guest_rate_price_data['Price (per Night)']][r]
                link = [str(x) for x in area_guest_rate_price_data['Link']][r]
                print('{}. {}'.format(r+1, title))
                print('******** {}({}) ********* ${}/night *********'.format(rate, reviews, price))
                print(link)
                print()
                r += 1
    else:
        print('*** Sorry, no result.')

            
main()

Welcome to the Airbnb Filter and Recomendation in DMV area!

DMV area

1. Washington DC
2. Virginia
3. Maryland
q. Quit the program

*** What are you going to stay in DMV area? (select number): 1

* 221 results *

*** Add guest (number): 1

* 27 results with below information *

***********************
            Counts
Rate Scale        
4.0-4.5          4
4.5-5.0         10
NaN             13
***********************


Rate Scale

1. Below 3.5
2. 3.5 - 4.0
3. 4.0 - 4.5
4. 4.5 - 5.0
q. Quit the program

*** What is your expected rating? (select number): 4

* 10 results with below information *

***********************
             Counts
Price Scale        
50-100            1
Below 50          9
***********************


Price Scale

1. Below $50
2. $50 - $100
3. $100 - $150
4. $150 - $200
5. Over $200
q. Quit the program

*** What is your expected price? (select number): 1


* 9 results *

******* Top 5 Recomendation *******

1. Simple Bare Necessities
******** 4.57(186.0) ********* $36/night *********
https://www.airbnb.com/rooms/26281304?previous_page_section_name=1000&federated_search_id=a0f4d7ac-0b56-4681-baa6-598044d0c87c


2. Small Cozy Room in Brookland, N.E.
******** 4.87(127.0) ********* $24/night *********
https://www.airbnb.com/rooms/19737092?previous_page_section_name=1000&federated_search_id=f542776d-2a01-4ede-87dd-33844b8fb152


3. Cozy bedroom near Fort Totten, behind Catholic U
******** 4.9(21.0) ********* $40/night *********
https://www.airbnb.com/rooms/41123506?previous_page_section_name=1000&federated_search_id=f1214137-4cad-42ad-a66e-f9118b257fc6


4. Private room. Free parking
******** 4.82(18.0) ********* $37/night *********
https://www.airbnb.com/rooms/40783246?previous_page_section_name=1000&federated_search_id=a945a82a-f86c-40db-ae00-fdca21170395


5. Compact and Clean, 4 blocks to Metro
******** 4.69(16.0) ********* $38/night *********
https://www.airbnb.com/rooms/35095359?previous_page_section_name=1000&federated_search_id=f542776d-2a01-4ede-87dd-33844b8fb152


DMV area

1. Washington DC
2. Virginia
3. Maryland
q. Quit the program

*** What are you going to stay in DMV area? (select number): q

*** Quit the program successful!

	Type	Location	Title	Number of Guest	Number of Bedroom	Studio	Number of Bed	Number of Bath	Self Check-in	Air Conditioning	...	Free parking	Elevator	Gym	Indoor fireplace	Pool	Rate (out of 5)	Reviews	Price (per Night)	Link	Area
0	Entire apartment	Washington	Private Basement-apt in Logan Circle DC!	2	1.0	No	1.0	1.0	Yes	Yes	...	No	No	No	No	No	4.48	26.0	53	https://www.airbnb.com/rooms/16048230?previous...	Washington DC
1	Private room	Washington	Private room w/ bathroom, cable TV, wifi, & ref.	2	1.0	No	1.0	1.0	Yes	Yes	...	No	No	No	No	No	4.78	64.0	39	https://www.airbnb.com/rooms/28388898?previous...	Washington DC
2	Entire apartment	Washington	Major price reduction. A fabulous studio!	2	NaN	Yes	1.0	1.0	Yes	Yes	...	No	No	No	No	No	4.92	393.0	63	https://www.airbnb.com/rooms/8353034?previous_...	Washington DC
3	Entire apartment	Washington	Lovely apartment close to everything	4	1.0	No	1.0	1.0	No	Yes	...	No	No	No	No	No	4.96	166.0	68	https://www.airbnb.com/rooms/22535385?previous...	Washington DC
4	Entire guesthouse	Washington	Garage Mahal	2	1.0	No	1.0	1.0	No	Yes	...	Yes	No	No	Yes	No	4.60	287.0	31	https://www.airbnb.com/rooms/2091153?previous_...	Washington DC

	Type	Location	Title	Number of Guest	Number of Bedroom	Studio	Number of Bed	Number of Bath	Self Check-in	Air Conditioning	...	Free parking	Elevator	Gym	Indoor fireplace	Pool	Rate (out of 5)	Reviews	Price (per Night)	Link	Area
0	Earth house	Broadway	Hobbit Style Underground Cabin	2	1.0	No	1.0	1.0	No	Yes	...	No	No	No	No	No	4.98	99.0	129	https://www.airbnb.com/rooms/42388319?previous...	Virginia
1	Yurt	Afton	Luxe Yurt w/Hot Tub in the Heart of the Blue R...	4	1.0	No	1.0	1.0	No	Yes	...	No	No	No	No	No	5.00	406.0	157	https://www.airbnb.com/rooms/14908682?previous...	Virginia
2	Entire cabin	Appomattox	Cozy and Private Riverfront Cabin on 50 Acres	2	1.0	No	1.0	1.0	No	Yes	...	No	No	No	No	No	5.00	33.0	199	https://www.airbnb.com/rooms/43466214?previous...	Virginia
3	Entire cabin	Maurertown	The Bear Den - Mountain Cabin w/ Spectacular V...	6	2.0	No	3.0	1.0	Yes	Yes	...	No	No	No	No	No	5.00	56.0	189	https://www.airbnb.com/rooms/39107053?previous...	Virginia
4	Entire cabin	Farmville	Weekend Getaway Cabin	4	1.0	No	1.0	1.0	Yes	Yes	...	No	No	No	No	No	4.93	153.0	129	https://www.airbnb.com/rooms/18506198?previous...	Virginia

	Type	Location	Title	Number of Guest	Number of Bedroom	Studio	Number of Bed	Number of Bath	Self Check-in	Air Conditioning	...	Free parking	Elevator	Gym	Indoor fireplace	Pool	Rate (out of 5)	Reviews	Price (per Night)	Link	Area
0	Entire apartment	Lexington Park	Adorable Waterfront Apartment Weekend Getaway	2	1.0	No	1.0	1.0	No	Yes	...	No	No	No	No	No	5.00	82.0	80	https://www.airbnb.com/rooms/36812815?previous...	Maryland
1	Entire guest suite	Catonsville	Cozy Catonsville Suite	2	1.0	No	1.0	1.0	No	Yes	...	No	No	No	No	No	4.90	129.0	50	https://www.airbnb.com/rooms/29596923?previous...	Maryland
2	Private room	Baltimore	Cozy Room2 -Shared Living Space	1	1.0	No	1.0	1.5	No	Yes	...	No	No	No	No	No	NaN	NaN	17	https://www.airbnb.com/rooms/43317323?previous...	Maryland
3	Tiny house	Saint Inigoes	Historic St.Mary's City at the Lazy Bear Cottage	2	1.0	No	1.0	1.0	No	Yes	...	No	No	No	No	No	4.99	148.0	69	https://www.airbnb.com/rooms/13544455?previous...	Maryland
4	Entire cabin	Freeland	Peaceful Rustic Retreat, Wild Flowers & Farm V...	2	1.0	No	1.0	1.0	No	Yes	...	Yes	No	No	Yes	No	5.00	26.0	84	https://www.airbnb.com/rooms/36936064?previous...	Maryland

	Type	Location	Title	Number of Guest	Number of Bedroom	Studio	Number of Bed	Number of Bath	Self Check-in	Air Conditioning	...	Free parking	Elevator	Gym	Indoor fireplace	Pool	Rate (out of 5)	Reviews	Price (per Night)	Link	Area
1	Entire apartment	Washington	Private Basement-apt in Logan Circle DC!	2	1.0	No	1.0	1.0	Yes	Yes	...	No	No	No	No	No	4.48	26.0	53	https://www.airbnb.com/rooms/16048230?previous...	Washington DC
2	Private room	Washington	Private room w/ bathroom, cable TV, wifi, & ref.	2	1.0	No	1.0	1.0	Yes	Yes	...	No	No	No	No	No	4.78	64.0	39	https://www.airbnb.com/rooms/28388898?previous...	Washington DC
3	Entire apartment	Washington	Major price reduction. A fabulous studio!	2	NaN	Yes	1.0	1.0	Yes	Yes	...	No	No	No	No	No	4.92	393.0	63	https://www.airbnb.com/rooms/8353034?previous_...	Washington DC
4	Entire apartment	Washington	Lovely apartment close to everything	4	1.0	No	1.0	1.0	No	Yes	...	No	No	No	No	No	4.96	166.0	68	https://www.airbnb.com/rooms/22535385?previous...	Washington DC
5	Entire guesthouse	Washington	Garage Mahal	2	1.0	No	1.0	1.0	No	Yes	...	Yes	No	No	Yes	No	4.60	287.0	31	https://www.airbnb.com/rooms/2091153?previous_...	Washington DC
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
702	Entire apartment	Baltimore	Business district, convention center, indoor p...	4	1.0	No	6.0	1.0	Yes	Yes	...	No	No	No	No	No	NaN	NaN	98	https://www.airbnb.com/rooms/46298481?previous...	Maryland
703	Entire chalet	McHenry	Fish R Landing @ Deep Creek Lake	10	3.0	No	6.0	2.0	Yes	Yes	...	No	No	No	No	No	4.78	49.0	276	https://www.airbnb.com/rooms/18890867?previous...	Maryland
704	Entire house	Chesapeake Beach	Staycation at Cozy Beach Home	11	4.0	No	7.0	2.5	Yes	Yes	...	No	No	No	No	No	4.42	26.0	132	https://www.airbnb.com/rooms/29857363?previous...	Maryland
705	Entire house	Silver Spring	Enjoy beautiful scenery at fully equipped 2BR ...	4	2.0	No	2.0	1.0	Yes	Yes	...	No	No	No	No	No	5.00	13.0	78	https://www.airbnb.com/rooms/43908736?previous...	Maryland
706	Entire house	Berlin	Dog-Friendly Berlin Home w/ Pool & Water Access!	6	2.0	No	3.0	1.0	No	Yes	...	No	No	No	No	No	4.63	16.0	111	https://www.airbnb.com/rooms/33937160?previous...	Maryland

	Type	Counts	Median Price (per Night)
23	Private room	155	35.0
7	Entire apartment	117	76.0
9	Entire cabin	91	151.0
15	Entire house	79	132.0
12	Entire cottage	48	130.5
13	Entire guest suite	45	68.0
14	Entire guesthouse	26	84.0
18	Entire townhouse	25	118.0
19	Farm stay	20	134.0
11	Entire condominium	16	72.5
17	Entire serviced apartment	14	110.0
30	Yurt	11	103.0
27	Tiny house	9	93.0
10	Entire chalet	7	206.0
24	Room	5	79.0
29	Treehouse	5	249.0
16	Entire loft	5	60.0
25	Shared room	5	28.0
0	Barn	4	157.5
22	Hotel room	3	119.0
20	Hostel beds	2	37.0
8	Entire bungalow	2	96.5
2	Bus	2	55.5
26	Tent	2	66.0
28	Tipi	2	81.0
3	Campsite	1	61.0
4	Castle	1	76.0
5	Dome house	1	96.0
1	Boat	1	119.0
6	Earth house	1	129.0
21	Hotel beds	1	45.0

Project 2: Analyzing Airbnb Data in DMV areas

II. Data Analyzing¶

1. Data Cleaning and Preprocessing¶

1.1 Import Package¶

1.2 Read CSV File into DataFrame¶

1.3 Concatenate three Data Sets¶

2. Data Exploration, Alalysis and Visualization¶

2.1 Common Location¶

2.2 Title Name Preference¶

2.3 Analysis of Property Type in DMV area¶

2.4 Correlation Coefficients Between Variables¶

2.5 Analysis of Room Structure in DMV area¶

2.5 Analysis of Amenities and Facilities of Lodging in DMV area¶

2.6 Popular Lodging with Best Price in DMV area¶

2.7 Interactive¶

3. Conclusion¶

4. Learning Processes¶

	Number of Guest	Number of Bedroom	Number of Bed	Number of Bath	Rate (out of 5)	Reviews	Price (per Night)	Air Conditioning_Yes	Wifi_Yes	Washer_Yes	Kitchen_Yes	Breakfast_Yes	Pets allowed_Yes	Free parking_Yes	Elevator_Yes	Gym_Yes	Indoor fireplace_Yes	Pool_Yes
Number of Guest	1.00	0.79	0.80	0.39	0.04	-0.03	0.61	-0.03	-0.02	-0.19	0.04	-0.02	-0.07	0.20	-0.04	-0.09	-0.02	-0.08
Number of Bedroom	0.79	1.00	0.75	0.48	0.02	-0.12	0.59	0.00	0.01	-0.15	0.06	-0.05	-0.09	0.16	-0.03	-0.07	0.00	-0.05
Number of Bed	0.80	0.75	1.00	0.45	0.04	-0.10	0.48	-0.01	-0.00	-0.14	0.03	-0.03	-0.07	0.16	-0.04	-0.11	0.03	-0.08
Number of Bath	0.39	0.48	0.45	1.00	-0.02	-0.14	0.37	0.05	0.05	-0.06	0.00	0.12	-0.06	0.04	0.03	-0.07	0.16	-0.04
Rate (out of 5)	0.04	0.02	0.04	-0.02	1.00	0.08	0.16	0.03	-0.08	-0.07	-0.08	0.07	-0.01	0.02	-0.10	-0.01	-0.05	-0.04
Reviews	-0.03	-0.12	-0.10	-0.14	0.08	1.00	-0.05	-0.08	-0.09	-0.11	-0.11	0.07	0.11	-0.05	-0.05	-0.10	0.01	-0.05
Price (per Night)	0.61	0.59	0.48	0.37	0.16	-0.05	1.00	-0.05	-0.08	-0.22	0.04	-0.03	-0.06	0.19	-0.02	-0.02	-0.05	0.00
Air Conditioning_Yes	-0.03	0.00	-0.01	0.05	0.03	-0.08	-0.05	1.00	0.20	0.15	-0.13	-0.00	0.01	-0.24	-0.11	-0.02	0.04	-0.08
Wifi_Yes	-0.02	0.01	-0.00	0.05	-0.08	-0.09	-0.08	0.20	1.00	0.22	0.37	-0.10	0.07	0.24	-0.08	0.07	0.13	0.04
Washer_Yes	-0.19	-0.15	-0.14	-0.06	-0.07	-0.11	-0.22	0.15	0.22	1.00	0.02	-0.08	-0.03	-0.23	-0.04	0.02	0.03	-0.00
Kitchen_Yes	0.04	0.06	0.03	0.00	-0.08	-0.11	0.04	-0.13	0.37	0.02	1.00	-0.20	-0.09	0.42	-0.13	-0.10	-0.15	-0.09
Breakfast_Yes	-0.02	-0.05	-0.03	0.12	0.07	0.07	-0.03	-0.00	-0.10	-0.08	-0.20	1.00	-0.02	-0.11	0.06	0.03	0.04	-0.03
Pets allowed_Yes	-0.07	-0.09	-0.07	-0.06	-0.01	0.11	-0.06	0.01	0.07	-0.03	-0.09	-0.02	1.00	-0.05	0.01	0.06	0.01	0.05
Free parking_Yes	0.20	0.16	0.16	0.04	0.02	-0.05	0.19	-0.24	0.24	-0.23	0.42	-0.11	-0.05	1.00	-0.12	-0.11	-0.08	-0.07
Elevator_Yes	-0.04	-0.03	-0.04	0.03	-0.10	-0.05	-0.02	-0.11	-0.08	-0.04	-0.13	0.06	0.01	-0.12	1.00	0.22	-0.05	0.13
Gym_Yes	-0.09	-0.07	-0.11	-0.07	-0.01	-0.10	-0.02	-0.02	0.07	0.02	-0.10	0.03	0.06	-0.11	0.22	1.00	-0.00	0.48
Indoor fireplace_Yes	-0.02	0.00	0.03	0.16	-0.05	0.01	-0.05	0.04	0.13	0.03	-0.15	0.04	0.01	-0.08	-0.05	-0.00	1.00	-0.03
Pool_Yes	-0.08	-0.05	-0.08	-0.04	-0.04	-0.05	0.00	-0.08	0.04	-0.00	-0.09	-0.03	0.05	-0.07	0.13	0.48	-0.03	1.00

	Type	Counts
0	Air Conditioning	559
1	Wifi	490
2	Washer	89
3	Kitchen	289
4	Breakfast	43
5	Pets allowed	27
6	Free parking	220
7	Elevator	22
8	Gym	19
9	Indoor fireplace	42
10	Pool	8

Area	Amentities and Facilities	Maryland	Virginia	Washington DC
0	Air Conditioning	93.305439	68.699187	75.565611
1	Wifi	92.050209	39.430894	78.280543
2	Washer	20.083682	0.406504	18.099548
3	Kitchen	44.769874	31.300813	47.511312
4	Breakfast	2.092050	9.349593	6.787330
5	Pets allowed	2.510460	2.032520	7.239819
6	Free parking	36.401674	45.121951	9.954751
7	Elevator	1.255230	0.000000	8.597285
8	Gym	2.092050	0.000000	6.334842
9	Indoor fireplace	10.460251	1.626016	5.882353
10	Pool	0.836820	0.000000	2.714932

	Type	Location	Title	Number of Guest	Number of Bedroom	Studio	Number of Bed	Number of Bath	Self Check-in	Air Conditioning	...	Free parking	Elevator	Gym	Indoor fireplace	Pool	Rate (out of 5)	Reviews	Price (per Night)	Link	Area
268	Private room	Stanardsville	Secluded Tree House (Safety Protocol Listed Be...	2	1.0	No	1.0	1.0	Yes	Yes	...	No	No	No	No	No	4.81	718.0	139	https://www.airbnb.com/rooms/886469?previous_p...	Virginia
235	Tipi	Fairfield	Tipi with a great view of the Blue Ridge Mount...	3	NaN	Yes	1.0	1.0	No	No	...	No	No	No	No	No	4.98	645.0	92	https://www.airbnb.com/rooms/12054355?previous...	Virginia
113	Entire apartment	Washington	@ 14th & U – 99.9% Clean - 99 Walk Score - Metro	3	1.0	No	2.0	1.0	Yes	Yes	...	No	No	No	No	No	4.88	562.0	124	https://www.airbnb.com/rooms/15373088?previous...	Washington DC
24	Entire townhouse	Washington	Brand new english basement in D.C.	3	1.0	No	1.0	1.0	Yes	No	...	No	No	No	No	No	4.94	530.0	71	https://www.airbnb.com/rooms/11640393?previous...	Washington DC
367	Entire apartment	Stanardsville	Suite Pea (Safety Protocol Listed Below)	2	1.0	No	1.0	1.0	Yes	Yes	...	Yes	No	No	No	No	4.75	484.0	79	https://www.airbnb.com/rooms/1608638?previous_...	Virginia
64	Entire apartment	Washington	Modern luxury in Shaw, short walk 2 metro/conv...	4	1.0	No	2.0	1.0	Yes	Yes	...	No	No	No	No	No	4.85	483.0	90	https://www.airbnb.com/rooms/6135500?previous_...	Washington DC
166	Entire apartment	Washington	Union Market Penthouse Apartment	4	1.0	No	2.0	1.0	Yes	No	...	No	No	No	No	No	4.44	443.0	124	https://www.airbnb.com/rooms/4545885?previous_...	Washington DC
52	Entire house	Washington	Capitol Hill luxury English basment	4	1.0	No	2.0	1.0	Yes	Yes	...	No	No	No	Yes	No	4.91	440.0	107	https://www.airbnb.com/rooms/3317645?previous_...	Washington DC
215	Entire apartment	Washington	Cozy in Foggy	2	NaN	Yes	1.0	1.0	No	Yes	...	No	No	No	No	No	4.84	408.0	67	https://www.airbnb.com/rooms/13199849?previous...	Washington DC
223	Yurt	Afton	Luxe Yurt w/Hot Tub in the Heart of the Blue R...	4	1.0	No	1.0	1.0	No	Yes	...	No	No	No	No	No	5.00	406.0	157	https://www.airbnb.com/rooms/14908682?previous...	Virginia